aws
Warn
Audited by Snyk on Jul 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the skill’s runtime is triggered by user text phrases (e.g., “AWS”, “VPC”, “Terraform AWS”, etc.), meaning outsider-authored free text is directly consumed as the LLM’s input for generating infrastructure artifacts.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata